Findings, implications and lessons learned

And some statistical facts:

• There was no significant correlation between viability and germination rate.

• By calculating components of variance from the analysis of variance it was possible to assess the suitability of the design for future experimentation

• The sample size calculations demonstrated that by distributing the sample by putting greater replication at the upper than lower layer would have improved the experimental design.

• We have also learnt a little about what happens to the contents of analysis of variance when we base the analysis on means rather than individual observations.